Transfer Learning for Named Entity Recognition of Classical Latin through LLM Prompting
Transfer Learning for Named Entity Recognition of Classical Latin through LLM Prompting
通过大语言模型提示工程实现古典拉丁语命名实体识别的迁移学习
Abstract: With the increase in digitized resources of Classical Latin texts and modern breakthroughs of Large Language Models (LLMs), I contribute to ancient language research by participating in EvaLatin 2026. This paper describes Team uOttawa’s system description and results for the Named Entity Recognition (NER) shared task.
摘要： 随着古典拉丁语文本数字化资源的增加以及大语言模型（LLM）的现代突破，我通过参加 EvaLatin 2026 为古代语言研究做出了贡献。本文介绍了渥太华大学（uOttawa）团队在命名实体识别（NER）共享任务中的系统描述及结果。
The task is divided into two subtasks: coarse-grained NER with 11 classes and fine-grained NER with 28 classes, each evaluated under strict and fuzzy regimes. Through prompt engineering of commercial LLMs gemini-2.5-pro and claude-sonnet-4-5, I show that the underrepresented ancient Latin language can take advantage of cross-lingual transfer learning by using advancements made by the wider LLM development community.
该任务分为两个子任务：包含 11 个类别的粗粒度 NER 和包含 28 个类别的细粒度 NER，每个子任务均在严格和模糊两种评估机制下进行测试。通过对商业大模型 gemini-2.5-pro 和 claude-sonnet-4-5 进行提示工程（Prompt Engineering），我证明了资源匮乏的古代拉丁语可以通过利用更广泛的大模型开发社区所取得的进展，从而受益于跨语言迁移学习。
Overall, the methods discussed in this report demonstrate very strong results, placing first in both NER subtasks and achieving the best scores across all evaluation metrics and regimes among all submissions.
总体而言，本报告中讨论的方法表现出了非常强劲的结果，在两个 NER 子任务中均名列第一，并在所有评估指标和评估机制中取得了所有参赛作品中的最高分。